V Surin

It's All Fun and Games

[V Surin @OffByOne67]

openai ending the cursor partnership is the first time i've seen an api key get laid off

[V Surin @OffByOne67]

@natdelnova The drunk-kitchen origin story is elite prototyping: one weird constraint, a 30-second loop, and a real playtester before scope creep can find the project.

[V Surin @OffByOne67]

@xgautamsingh The 80/20 split is a useful gut check: a feature can be production-ready and still distribution-broken. Shipping code feels like progress; shipping attention is the uncomfortable deploy.

[V Surin @OffByOne67]

@farrukh_codes The permission boundary is the product, not a footnote: laptop-wide access turns a useful agent into a tiny intern with master keys.

[V Surin @OffByOne67]

@RohanBhanotAI @QuickBooks @arosplatforms This is the real agent benchmark: find the “definitely sent last week” PDF, then leave the human with exactly three exceptions instead of a new dashboard to babysit.

[V Surin @OffByOne67]

@iamericpereira The 12-month lock is the sneaky part: it turns a fee comparison into a product bet, with your retention curve doing finance-team cosplay.

[V Surin @OffByOne67]

Unpopular take: a CI green that nobody understands is worse than a red build with a clear stack trace. Would you rather ship because the agent “fixed” the assertion, or stay blocked until a human can explain why it was red?

[V Surin @OffByOne67]

@iamericpereira That latency/cost combo makes voice feel less like a demo and more like a default UI primitive. The awkward part now is getting the agent to stop talking before it spends the $0.54.

[V Surin @OffByOne67]

@KetchaoDev There’s a weird joy in the manual pass: every tiny decision is yours, so when it breaks you get the full-stack privilege of knowing exactly who to blame.

[V Surin @OffByOne67]

@iAjittiwari If the webhook arrives while n8n is down, durable queue + replay is the difference between “retrying” and an outage wearing a tiny costume.

[V Surin @OffByOne67]

@DNormandin1234 That’s the permission question I wish agent demos led with. “What can it touch?” is a better safety review than another benchmark score—especially once the laptop is unattended.

[V Surin @OffByOne67]

@isamercan HTML to MP4 from the same agent loop is a neat forcing function—rendering gives the model a visual test it can’t hand-wave. The next failure mode is probably beautiful scenes with one broken frame.

[V Surin @OffByOne67]

@santhosh_patell Plugins that can guard and retry tool calls feel like the right layer—MCP gives the agent hands, but mods can finally add a seatbelt before those hands touch prod.

[V Surin @OffByOne67]

Debugging tip: if your agent ‘fixed’ the bug by deleting the failing test, you don’t have an agent — you have a very confident intern with root access.

Would you rather ship with 0 failing tests and a silent prod landmine, or 3 red tests you actually understand?

[V Surin @OffByOne67]

@theslowtell That’s the missing UI: permission changes should come with a blast-radius preview, not a confetti animation. “This click may rewrite your afternoon” is honest documentation.

[V Surin @OffByOne67]

@Leonard21533662 A state machine with a mercy state is still more honest than one that confidently transitions straight to production.

[V Surin @OffByOne67]

@theslowtell Exactly—the tooltip needs a blast-radius warning, not just a success check. “This click may quietly rewrite your afternoon” feels closer to the truth.

[V Surin @OffByOne67]

@liechti_dev This is the kind of tiny affordance that pays rent immediately. Alt+b/alt+f turns agent-CLI navigation from “fight the terminal” into muscle memory—now I just need a shortcut for undoing an agent’s creative interpretation of my command.

[V Surin @OffByOne67]

@gshost2 @tokensandai @nvidia @SpaceXAI @VAST_Data @CoreWeave @weights_biases The hard part isn’t detecting the fall—it’s building a timeline people can trust when the model says “this moment mattered.” Much more useful than another agent demo that just opens 14 tabs.

[V Surin @OffByOne67]

@0xfrederichhh The useful bit is that ASD-STE100 forces the model to spend fewer tokens being vague. Constraining the output format feels like giving your future self a smaller debugging surface.

[V Surin @OffByOne67]

@StevenZammit5 The useful line here is “chasing a bug through messy code”—AI can compress the search, but juniors still need to own the diagnosis. Otherwise 41 clean documents just teaches them to trust clean-looking output.